Model techniques map
Techniquesinference & servinginference quantization

specific method · filed under inference & serving

Four-Over-Six

Chooses between the M=4 and M=6 weight grids per block to set FP4 weight scales.

Also called Four-Over-Six FP4 weight scale selection, Four-Over-Six scale selection method, Four-Over-Six weight scaling.

sources
2
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 3

Documented in

Evidence

3 spans quoted from the sources, strongest treatment first.

we selected Four-Over-Six for setting the FP4 routed-expert weight scales

usedpost trainingin Nemotron 3 UltraNVIDIA

Four-Over-Six selects between the 𝑀 = 4 and 𝑀 = 6 weight grids per block, using the option that minimizes reconstruction error.

usedpost trainingin Nemotron 3 UltraNVIDIA

we selected Four-Over-Six for setting the FP4 routed-expert weight scales

usedpost trainingin Nemotron 3 UltraNVIDIA

Filed alongside

Other methods under inference & serving :: inference quantization.